{"title":"Analysis of Feature Parameters for Objective Stress Assessment of Indoor Noises","authors":"Kwang Myung Jeon, H. Kim","doi":"10.1109/AIMS.2015.64","DOIUrl":null,"url":null,"abstract":"This paper investigates the effect of feature parameters on the objective assessment of stress under indoor noise conditions. To this end, both a qualitative stress parameter and quantitative feature parameters are collected according to different sequences of indoor noises. In other words, the qualitative stress parameter is obtained by continuously logging the perceptual intensity of stress for a certain period with a score ranging from 1 to 10 under indoor noise conditions. In addition, the quantitative feature parameters are represented by the combination of various audio feature parameters consisting of psychoacoustic, spectral, and temporal features. Finally, multiple linear regression analysis is conducted on the pairs of the qualitative stress parameter and possible combinations of quantitative feature parameters. It is shown from the evaluation that combinations of feature parameters could have a coefficient of determination of up to 0.9607.","PeriodicalId":121874,"journal":{"name":"2015 3rd International Conference on Artificial Intelligence, Modelling and Simulation (AIMS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 3rd International Conference on Artificial Intelligence, Modelling and Simulation (AIMS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/AIMS.2015.64","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
This paper investigates the effect of feature parameters on the objective assessment of stress under indoor noise conditions. To this end, both a qualitative stress parameter and quantitative feature parameters are collected according to different sequences of indoor noises. In other words, the qualitative stress parameter is obtained by continuously logging the perceptual intensity of stress for a certain period with a score ranging from 1 to 10 under indoor noise conditions. In addition, the quantitative feature parameters are represented by the combination of various audio feature parameters consisting of psychoacoustic, spectral, and temporal features. Finally, multiple linear regression analysis is conducted on the pairs of the qualitative stress parameter and possible combinations of quantitative feature parameters. It is shown from the evaluation that combinations of feature parameters could have a coefficient of determination of up to 0.9607.